{"id":"W3018974563","doi":"10.1186/s12911-020-1089-0","title":"Development and validation of data quality rules in administrative health data using association rule mining","year":2020,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Health; University of Calgary; Alberta Health Services","funders":"Canadian Institutes of Health Research","keywords":"Association rule learning; Data mining; Coding (social sciences); Data quality; Variance (accounting); Computer science; Delphi method; Health informatics; Quality (philosophy); Data set; Medicine; Statistics; Artificial intelligence; Operations management; Mathematics; Public health; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4387654,0.001670613,0.002925598,0.01569749,0.00302801,0.01049645,0.005571396,0.001892908,0.0008222555],"category_scores_gemma":[0.6379848,0.001217364,0.004562963,0.01204813,0.003551542,0.005562888,0.004735731,0.004453453,0.0004942809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006412446,"about_ca_system_score_gemma":0.01899699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009369224,"about_ca_topic_score_gemma":0.007616523,"domain_scores_codex":[0.5520372,0.2642913,0.09067889,0.02164357,0.06849715,0.002851925],"domain_scores_gemma":[0.117863,0.6948104,0.05997911,0.04136756,0.08466872,0.001311221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006761501,0.001151633,0.4166222,0.01143829,0.003110416,0.0008348503,0.02051181,0.04509933,0.005770444,0.03061365,0.01200562,0.4521657],"study_design_scores_gemma":[0.0007681377,0.001628933,0.1952307,0.02690831,0.003197671,0.001716219,0.02198252,0.5054259,0.03904356,0.1248866,0.07827561,0.0009357827],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.131869,0.001633994,0.8368487,0.005317898,0.0002620066,0.01270726,0.004748973,0.001278456,0.005333622],"genre_scores_gemma":[0.1444058,0.0003929537,0.8456752,0.000579083,0.00006402085,0.004770906,0.003858021,0.00009977495,0.0001543733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4387654,"threshold_uncertainty_score":0.6921022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7776327660639315,"score_gpt":0.6048172612575257,"score_spread":0.1728155048064058,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}